Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
We present Skywork R1V2, a next-generation multimodal reasoning model and a major leap forward from its predecessor, Skywork R1V. At its core, R1V2 introduces a hybrid reinforcement learning paradigm that harmonizes reward-model guidance with rule-based strategies, thereby addressing the long-standing challenge of balancing sophisticated reasoning capabilities with broad generalization. To further enhance training efficiency, we propose the Selective Sample Buffer (SSB) mechanism, which effectively counters the ``Vanishing Advantages'' dilemma inherent in Group Relative Policy Optimization (GRPO) by prioritizing high-value samples throughout the optimization process. Notably, we observe that excessive reinforcement signals can induce visual hallucinations--a phenomenon we systematically monitor and mitigate through calibrated reward thresholds throughout the training process. Empirical results affirm the exceptional capability of R1V2, with benchmark-leading performances such as 62.6 on OlympiadBench, 79.0 on AIME2024, 63.6 on LiveCodeBench, and 74.0 on MMMU. These results underscore R1V2's superiority over existing open-source models and demonstrate significant progress in closing the performance gap with premier proprietary systems, including Gemini 2.5 and OpenAI o4-mini. The Skywork R1V2 model weights have been publicly released to promote openness and reproducibility https://huggingface.co/Skywork/Skywork-R1V2-38B.
Code (1)
Tasks
Multimodal Reasoningreinforcement-learningReinforcement LearningSimilar Papers 제목 키워드 기반
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, S…
Language ModelingLanguage ModellingMultimodal ReasoningSkywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Despite recent progress in multimodal agentic systems, existing approaches often treat image manipulation and web search as disjoint capabilities, rely heavily on costly reinforcement learning, and lack planning grounded…
Reinforcement LearningImage ManipulationSkywork-R1V3 Technical Report
We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large …
cross-modal alignmentMathematical ReasoningMultimodal ReasoningVisual ReasoningSkywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
We propose Skywork-VL Reward, a multimodal reward model that provides reward signals for both multimodal understanding and reasoning tasks. Our technical approach comprises two key components: First, we construct a large…
Multimodal ReasoningSkywork Open Reasoner 1 Technical Report
The success of DeepSeek-R1 underscores the significant role of reinforcement learning (RL) in enhancing the reasoning capabilities of large language models (LLMs). In this work, we present Skywork-OR1, an effective and s…
MathReinforcement Learning (RL)